Side-by-side comparison
GPT-3.5 Turbo (older v0613) vs Devstral Medium
OpenAI
GPT-3.5 Turbo (older v0613)
🔧 Tools
{} JSON
Input / 1M
$1.0000
Output / 1M
$2.0000
Mistral
Devstral Medium
🔧 Tools
{} JSON
Input / 1M
$0.4000
Output / 1M
$2.0000
| GPT-3.5 Turbo (older v0613) | Devstral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 4,095 | 131,072 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools, json_mode | tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 1.0000 | 0.4000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 2.0000 | 2.0000 |
Frequently asked questions
Which is cheaper, GPT-3.5 Turbo (older v0613) or Devstral Medium?
Devstral Medium is cheaper than GPT-3.5 Turbo (older v0613) on a 50/50 input/output blend by about $0.3 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, GPT-3.5 Turbo (older v0613) or Devstral Medium?
Devstral Medium has the larger context window at 131k tokens versus 4k tokens for GPT-3.5 Turbo (older v0613). That means Devstral Medium can ingest about 32.0x as much text per request.
What is the difference between GPT-3.5 Turbo (older v0613) and Devstral Medium?
GPT-3.5 Turbo (older v0613) comes from OpenAI; Devstral Medium comes from Mistral. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.